Topics
53 curated papers across all published weeks — sorted by disruptiveness score.
Humanoid loco-manipulation requires coordinated locomotion, balance regulation, and manipulation under frequent contacts, making teleoperated demonstration col…
Read free explainer →
2026-W47
Dexterous in-hand manipulation of a grasped object with an anthropomorphic hand is an unsolved frontier for robot dexterity. The contact-richness and highly dy…
2026-W38
World Action Models (WAMs) advance beyond conventional visuomotor policies by jointly predicting future world states and robot actions, enabling the policy to…
2026-W39
Generalist robot policies benefit from large-scale visual pretraining but often struggle with contact-rich dexterous manipulation, where force, compliance, and…
2026-W43
We present OpenTac, a novel sensor and a full-stack ecosystem for tactile skins that are highly customizable, scalable, and readily deployed in downstream robo…
2026-W44
General-purpose robots must perform a wide range of tasks from agile locomotion to dexterous manipulation. While sim-to-real reinforcement learning (RL) has pr…
2026-W42
We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills, improvin…
2026-W41
Human demonstrations are a scalable data source for learning dexterous manipulation, but the embodiment gap prevents human motion from being executed directly…
Humanoid robots are typically trained as solitary agents, leaving them unable to coordinate physically with human partners who naturally anticipate and adjust…
2026-W46
Reliable surgical planning requires models to anticipate not only how instruments will move, but also how the operative visual state will evolve together with…
2026-W36
Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perce…
While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demonstrations, many recent methods predominantl…
Autonomous laboratories hold great promise for accelerating scientific discovery. To achieve this vision, robots are supposed to dexterously manipulate diverse…
2026-W34
The capability to perceive and synthesize human-human interactions is fundamental to developing intelligent digital human systems. However, existing datasets a…
2026-W35
Vision-Language-Action (VLA) models have emerged as powerful foundations for robotic manipulation, but their reliance on fixed camera configurations during tra…
Robot manipulation in everyday environments inherently involves substantial tool usage. Seemingly simple household tasks, such as cooking pan-fried tofu, requi…
2026-W45
As robotic hardware and learning methods advance, humanoids need tools to perform tasks beyond their inherent physical limits. Successful tool use requires sel…
Vision-language pre-training and predictive world modeling provide robot policies with rich semantic and dynamic visual features, but their native action and v…
2026-W37
Muscle-driven locomotion provides a physically grounded approach to generating realistic human movement. However, achieving both physiological plausibility and…
Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this…
Teaching a humanoid to follow instructions with its whole body runs into two obstacles. Its action space is large and tightly coupled: legs, arms, and fingers…
Learning dexterous manipulation from limited visual demonstrations is challenging because policies must acquire both perceptual grounding and precise control,…
World action models (WAMs) combine robot action generation with future state prediction. Existing WAMs typically predict videos or learned visual latents, whic…
Robotic harvesting requires precise manipulation to ensure accurate positioning of the end-effector, especially in a constraint workspace. This study introduce…
Visuomotor policies trained through imitation learning are highly sensitive to changes in camera viewpoint. This is particularly problematic for mobile manipul…
While Vision-Language-Action (VLA) models demonstrate impressive capabilities in robotic manipulation, their memoryless nature renders them brittle to test-tim…
2026-W40
Long-horizon robotic manipulation fundamentally requires memory: agents must retain task-relevant information from past observations and interactions and use i…
Personalization is essential for general-purpose robots to transition into household environments and achieve true practicality. While general robotic manipula…
We train a large-scale transformer policy on heterogeneous humanoid datasets that zero-shot adapts to new morphologies and terrains, combining imitation, reinf…
2026-W30
Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points across o…
We introduce P$^{3}$-WAM, a unified world action model for egocentric dexterous manipulation that learns 3D perception, action-conditioned prediction, and goal…
Embodied interaction requires an agent to integrate multimodal perception with verbal and nonverbal behaviors to effectively communicate its intentions, includ…
Quadruped robots have demonstrated impressive agility in parkour locomotion across complex terrains. However, most systems still rely on human intervention for…
Embodied foundation models hinge on diverse robot interaction data, which are costly to collect. Egocentric human videos offer a complementary source of experi…
Action-conditioned world models allow robots to predict the future consequences of candidate actions without additional physical interaction, supporting policy…
Humanoid mobility over complex terrain requires accurate foot placement and coordinated whole-body motion capable of robust adaptation. Reinforcement learning…
How effectively can vision-language-action (VLA) models learn diverse language-conditioned behaviors as training data scales? Investigating this question requi…
An autonomous laboratory combines literature-trained language models, Bayesian optimization, and robotic synthesis to discover three previously unreported soli…
This paper presents a low-cost, open experimental platform for research in end-to-end autonomous driving with miniature Ackermann vehicles. The platform combin…
We integrate high-resolution tactile sensing into vision-language-action models, enabling contact-rich assembly tasks that pure vision policies fail, with stro…
Reinforcement learning constitutes a promising approach owing to its potential for superhuman performance and self-learned policies. However, its application t…
Egocentric video offers scalable manipulation data for embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe object occlusi…
We demonstrate onboard optical navigation using lunar landmarks and star trackers that maintains kilometer-level accuracy throughout cis-lunar transfer without…
Fine-grained manipulation requires a robot policy to follow instructions, remain robust to visual variations, and translate predicted actions into precise robo…
Personalized interpretation of medical reports has emerged as an increasingly important need among patients. Addressing this need requires both evidence-ground…
World Action Models (WAMs) improve robot policy learning by incorporating future dynamics, yet explicitly generating future videos at inference introduces subs…
We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic onboard sensing for whole-body humanoid d…
2026-W31
In contact-rich manipulation, action multimodality and reactivity dominate different stages of a single episode. Before contact, multiple trajectories might be…
Pretraining navigation diffusion policies rely on large-scale expert demonstrations. These data are typically generated by a fully-informed oracle planner suit…
Vision-language-action models (VLAs) are moving rapidly towards deployment as general-purpose manipulation policies, but we currently lack basic tools for unde…
2026-W33
Contact-rich manipulation failures are often detected only after the robot has committed to contact. This is especially limiting in wrist-camera setups: close…
We consider the problem of autonomously learning robot skills under a limited practice budget for sequential tasks. We propose an active skill learning algorit…
We present \textbf{DreamX-Phi 1.0}, an action-conditioned video world model for robotic manipulation that, given an observed frame, a language instruction, and…